Core Files Management

ReviewAudited by ClawScan on May 8, 2026.

Overview

This is a local, instruction-only workspace file manager; it is purpose-aligned, but it can read and change persistent OpenClaw core, memory, and startup files.

Install only if you want an agent to help manage OpenClaw core workspace files. Before allowing writes, ask for a diff or summary, make sure backups exist, and avoid storing passwords, tokens, or other secrets in user.md, memory.md, or tools.md.

Findings (3)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

What this means

Personal preferences, infrastructure details, and remembered facts may be exposed to the agent context or persisted for later use.

Why it was flagged

The managed files include user context and long-term memory, so the skill may read or update sensitive and persistent information used in future tasks.

Skill content
| 4 | **user.md** | User context | User's info, preferences, infrastructure | ... | 5 | **memory.md** | Long-term memory | Important events, key configs, workflows |
Recommendation

Review proposed changes to user.md and memory.md, avoid storing secrets there, and keep backups before accepting edits.

What this means

If used incorrectly, the agent could overwrite or restore the wrong workspace Markdown content.

Why it was flagged

The skill asks the agent to use local read/write tools and optionally exec for file operations. This is expected for a file-management skill and the examples are scoped to the workspace, but it can still mutate local files.

Skill content
| `read` | Read core files | Required | ... | `write` | Modify core files | Required | ... | `exec` | Verify file status, backup | Optional |
Recommendation

Ask the agent to show diffs or summaries before writing changes, and confirm that backups were created.

What this means

Incorrect edits to agents.md or bootstrap.md could change future agent behavior until corrected.

Why it was flagged

The skill manages persistent operational and startup files that can influence future agent sessions. A bad edit could carry forward across later tasks.

Skill content
| 3 | **agents.md** | Logic & procedures manual | Specs, workspace rules, heartbeat, red lines | ... | **bootstrap.md** | Machine startup sequence | NOT soul — machine boot order only |
Recommendation

Keep edits narrow, preserve backups, and inspect changes to operational or startup rules before relying on the workspace again.